English | MP4 | AVC 1280×720 | AAC 44KHz 2ch | 43 lectures (5h 59m) | 2.41 GB
Build real world applications with Large Language Models and LangChain!
Welcome to the LangChain Udemy course: Unlock the Power of Language Models with Python!
Ready to develop cutting-edge applications powered by language models? LangChain is the framework you need. With LangChain, create data-aware and agentic applications that connect language models with other data sources and enable interaction with the environment.
Why Choose LangChain?
LangChain offers numerous benefits for your language model development needs:
Components: LangChain provides modular and user-friendly abstractions for working with language models, along with a wide range of implementations.
Off-the-shelf chains: Start building applications quickly with pre-built chains designed for specific tasks. Modify existing chains or create new ones for more complex or customized use-cases.
LangChain Modules:
- LangChain offers standard interfaces and external integrations for various modules:
- Model I/O: Easily interface with language models.
- Data connection: Connect with application-specific data sources.
- Chains: Construct sequences of calls to accomplish specific tasks.
- Agents: Enable chains to choose tools based on high-level directives.
- Memory: Persist application state between runs of a chain.
- Callbacks: Log and stream intermediate steps of any chain.
With LangChain you’ll be able to quickly build real world applications that directly sync up with Large Language Models, such as OpenAI’s GPT-4 API!
Revolutionize your applications with the power of language models. Enroll in our LangChain Udemy course now and unlock limitless possibilities!
What you’ll learn
- Learn to use LangChain for Model Inputs and Outputs to easily switch out LLMs.
- Discover how to perform data connections with Vector Databases such as ChromaDB with your LLMs and Langchain.
- Understand how to utilize LangChain memory to keep track of User and AI conversations.
- Use LangChain to build out custom agents to accomplish tasks with LLMs.
Table of Contents
Introduction
1 Introduction
Models – Input and Outputs
2 Introduction to Models – Inputs and Outputs
3 Using LLMs with LangChain
4 Chat Models with LangChain
5 Prompt Templates
6 Prompt and Models – Exercise
7 Prompt and Models – Exercise Solution
8 Few Shot Prompt Template
9 Parsing Output – Part One
10 Parsing Output – Part Two
11 Parsing Output – Part Three
12 Serialization -Saving and Loading Prompts
13 Models – Inputs and Outputs – Project Exercise
14 Models – Inputs and Outputs – Project Exercise Solution
Data Connections
15 Introduction to Data Connections
16 Document Loaders – Part One
17 Document Loaders – Integrations
18 Document Loading Exercise
19 Document Loading Exercise – Solution
20 Document Transformers
21 Text Embedding
22 Vector Store
23 Vector Store – Retrievers
24 MultiQuery Retrieval
25 Context Compression
26 Data Connections Exercise
27 Data Connections Exercise – Solutions
Chains
28 Introduction to LangChain Chains
29 LLMChain Object
30 SimpleSequentialChain
31 SequentialChain
32 LLMRouterChain
33 TransformChain
34 OpenAI Function Calling with LangChain
35 MathChain
36 Additional Chains – QA Documents
37 Chains – Exercise
38 Chains – Exercise Solution
Memory
39 Introduction to Memory
40 ChatMessageHistory Object
41 ConversationBufferMemory
42 ConversationBufferWindowMemory
43 ConversationSummaryMemory
Resolve the captcha to access the links!